GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → dongheehand → RCAN-tf

dongheehand / RCAN-tf

Licence: other
TensorFlow code for ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

deep-learningtensorflowcnnsuper-resolutionimage-restorationsuperresolution

Projects that are alternatives of or similar to RCAN-tf

DLSS
Deep Learning Super Sampling with Deep Convolutional Generative Adversarial Networks.
Stars: ✭ 88 (+252%)
Mutual labels:  cnn, super-resolution
Anime4k
A High-Quality Real Time Upscaler for Anime Video
Stars: ✭ 14,083 (+56232%)
Mutual labels:  cnn, super-resolution
Srgan Tensorflow
Tensorflow implementation of the SRGAN algorithm for single image super-resolution
Stars: ✭ 754 (+2916%)
Mutual labels:  cnn, super-resolution
Pytorch Srgan
A modern PyTorch implementation of SRGAN
Stars: ✭ 289 (+1056%)
Mutual labels:  cnn, super-resolution
AI-Lossless-Zoomer
AI无损放大工具
Stars: ✭ 940 (+3660%)
Mutual labels:  super-resolution, image-restoration
Srmd
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018) (Matlab)
Stars: ✭ 333 (+1232%)
Mutual labels:  cnn, super-resolution
Reproducible Image Denoising State Of The Art
Collection of popular and reproducible image denoising works.
Stars: ✭ 1,776 (+7004%)
Mutual labels:  cnn, image-restoration
Cfsrcnn
Coarse-to-Fine CNN for Image Super-Resolution (IEEE Transactions on Multimedia,2020)
Stars: ✭ 84 (+236%)
Mutual labels:  cnn, super-resolution
pytorch-gans
PyTorch implementation of GANs (Generative Adversarial Networks). DCGAN, Pix2Pix, CycleGAN, SRGAN
Stars: ✭ 21 (-16%)
Mutual labels:  super-resolution, superresolution
Srgan
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 2,641 (+10464%)
Mutual labels:  cnn, super-resolution
traiNNer
traiNNer: Deep learning framework for image and video super-resolution, restoration and image-to-image translation, for training and testing.
Stars: ✭ 130 (+420%)
Mutual labels:  super-resolution, image-restoration
Super-Resolution-Meta-Attention-Networks
Open source single image super-resolution toolbox containing various functionality for training a diverse number of state-of-the-art super-resolution models. Also acts as the companion code for the IEEE signal processing letters paper titled 'Improving Super-Resolution Performance using Meta-Attention Layers’.
Stars: ✭ 17 (-32%)
Mutual labels:  super-resolution, image-restoration
SwinIR
SwinIR: Image Restoration Using Swin Transformer (official repository)
Stars: ✭ 1,260 (+4940%)
Mutual labels:  super-resolution, image-restoration
Fast Srgan
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
Stars: ✭ 417 (+1568%)
Mutual labels:  cnn, super-resolution
Iseebetter
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
Stars: ✭ 202 (+708%)
Mutual labels:  cnn, super-resolution
sparse-deconv-py
Official Python implementation of the 'Sparse deconvolution'-v0.3.0
Stars: ✭ 18 (-28%)
Mutual labels:  super-resolution, image-restoration
LightFieldReconstruction
High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction
Stars: ✭ 50 (+100%)
Mutual labels:  super-resolution, image-restoration
mSRGAN-A-GAN-for-single-image-super-resolution-on-high-content-screening-microscopy-images.
Generative Adversarial Network for single image super-resolution in high content screening microscopy images
Stars: ✭ 52 (+108%)
Mutual labels:  super-resolution
RAMS
Official TensorFlow code for paper "Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks".
Stars: ✭ 55 (+120%)
Mutual labels:  super-resolution
MIRNet
Tensorflow implementation of MIRNet for Low-light image enhancement
Stars: ✭ 78 (+212%)
Mutual labels:  image-restoration
View All Similar Projects ➔

Image Super-Resolution Using Very Deep Residual Channel Attention Networks

An implementation of RCAN described in the paper using tensorflow. Image Super-Resolution Using Very Deep Residual Channel Attention Networks

Published in ECCV 2018, written by Y. Zhang, K. Li, L. Wang, B. Zhong, and Y. Fu

Requirement

  • Python 3.6.5
  • Tensorflow 1.13.1
  • Pillow 6.0.0
  • numpy 1.15.0
  • scikit-image 0.15.0

Datasets

Pre-trained model

Train using your own dataset

python main.py --train_GT_path ./GT_path --train_LR_path ./LR_path --test_GT_path ./test_GT_path --test_LR_path ./test_LR_path --test_with_train True --scale 2(or 3, 4, ...) --log_freq 1000
  • LR image and HR image pair should have same index when they are sorted by name respectively.
  • You can refer to the script file (run.sh) in my repository

Test using benchmarks

  1. Download pre-trained model.
  1. Unzip the pre-trained model file
tar -cvf model.tar
  1. Test using benchmarks
python main.py --mode test --pre_trained_model ./model/RCAN_X2(or 3, 4) --test_LR_path ./benchmark_LR_path --test_GT_path ./benchmark_GT_path --scale 2(or 3, 4) --self_ensemble False

If you want to use self_ensemble, --self_ensemble option to True

  • You can refer to the script file (run.sh) in my repository

Inference your own images

  1. Download pre-trained model.
  1. Unzip the pre-trained model file
tar -cvf model.tar
  1. Inference your own images
python main.py --mode test_only --pre_trained_model ./model/RCAN_X2(or 3, 4) --test_LR_path ./your_own_images --scale 2(or 3, 4) --chop_forward False

If your images are too large, OOM error can occur. In that case, --chop_forward option to True

Experimental Results

Qunatitative Results

Method Scale Set5 Set14 B100 Urban100
Bicubic X2 33.66 / 0.9299 30.24 / 0.8688 29.56 / 0.8431 26.88 / 0.8403
RDN X2 38.24 / 0.9614 34.01 / 0.9212 32.34 / 0.9017 32.89 / 0.9353
RCAN(paper) X2 38.27 / 0.9614 34.12 / 0.9216 32.41 / 0.9027 33.34 / 0.9384
RCAN(my results) X2 38.25 / 0.9615 34.07 / 0.9216 32.36 / 0.9020 33.12 / 0.9367
Method Scale Set5 Set14 B100 Urban100
Bicubic X3 30.39 / 0.8682 27.55 / 0.7742 27.21 / 0.7385 24.46 / 0.7349
RDN X3 34.71 / 0.9296 30.57 / 0.8468 29.26 / 0.8093 28.80 / 0.8653
RCAN(paper) X3 34.74 / 0.9299 30.65 / 0.8482 29.32 / 0.8111 29.09 / 0.8702
RCAN(my results) X3 34.75 / 0.9302 30.61 / 0.8470 29.31 / 0.8105 29.03 / 0.8693
Method Scale Set5 Set14 B100 Urban100
Bicubic X4 28.42 / 0.8104 26.00 / 0.7027 25.96 / 0.6675 23.14 / 0.6577
RDN X4 32.47 / 0.8990 28.81 / 0.7871 27.72 / 0.7419 26.61 / 0.8028
RCAN(paper) X4 32.63 / 0.9002 28.87 / 0.7889 27.77 / 0.7436 26.82 / 0.8087
RCAN(my results) X4 32.56 / 0.8996 28.89 / 0.7891 27.78 / 0.7434 26.81 / 0.8079

Qualitative results are will be updated soon!

Comments

If you have any questions or comments on my codes, please email to me. [email protected]

Reference

[1] https://github.com/yulunzhang/RCAN

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].